How do I use preprint-fulltext?

1. Click on "Install Server". 2. Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state. 3. In the chat, type @ followed by the MCP server name and your instructions, e.g., "@preprint-fulltext search for preprints on CRISPR in bioRxiv" That's it! The server will respond to your query, and you can continue using it as needed. Here is a step-by-step guide with screenshots.

preprint-fulltext

by genecell

Overview Schema Related Servers Score Discussions

Python

Local

preprint-fulltext

PyPI Python License: BSD-3-Clause

Retrieve the full text of bioRxiv / medRxiv / arXiv preprints as clean, structured, embedding-ready data — from a CLI, a Python library, or an MCP server.

preprint-fulltext turns a DOI (or a search) into structured sections (abstract / introduction / methods / results / discussion), a single JSON/Markdown document, or a chunked JSONL/Parquet corpus ready for embeddings and RAG. openRxiv text-and-data-mining (TDM) compliance is enforced structurally, not left to the user.

"Embedding-ready" means the output is clean, section-aware, token-bounded chunks — ready to feed to your embedding model. Computing embeddings is an optional last step you own; this tool does not bundle an embedding model.

Why · Who it's for · Full text for AI-driven science
Features · Install · Quickstart (CLI) · Typical workflows
Python library · MCP server (coding agents) · Data sources & routing
Configuration · Compliance · Development · Contact · License

Related MCP server: search-papers

Why

Preprint full text is scattered across incompatible channels: Europe PMC serves JATS XML for the open-access subset, the openRxiv S3 buckets hold the authoritative .meca corpus (requester-pays), OpenAlex is a catalog with n-gram-only full-text search, and the bioRxiv/medRxiv websites render HTML. preprint-fulltext unifies them behind one canonical data model and one shared JATS parser, so you get the same structured output no matter where a document came from.

Who it's for

ML / NLP researchers building embedding corpora or RAG systems over the preprint literature.
Bioinformaticians and labs who need a paper's methods/results as clean text for analysis, extraction, or LLM pipelines.
Coding agents (via the MCP server / SKILL.md) that need to pull a preprint's full text or search the literature mid-task.
Anyone who wants one preprint's sections from a DOI without hand-parsing JATS or scraping HTML.

Full text for AI-driven science

Language models and agents reason far more reliably over a paper's methods and results than over its abstract alone — most scientific claims, protocols, quantities, and caveats live in the body. preprint-fulltext gives Claude, Codex, and other agents that body as clean, section-labeled, provenance- and license-tagged text, which is the substrate for grounded scientific reasoning and deep research:

Literature deep-research — read across many papers' full text, not just abstracts.
Methods / protocol extraction — pull exact procedures, parameters, and datasets.
Claim verification — check a stated result against the actual Results section.
Reproducibility & meta-analysis — compare methods and numbers across studies.
RAG over your own corpus — section-aware, token-bounded chunks with citations.

Because every Section/Chunk carries its kind (methods / results / …), source, and license, an agent can cite precisely (which section of which paper/version) and stay within-license while it reasons. Full text is retrieval, not memorization: the model grounds its reasoning in the primary source instead of recalling a possibly-stale summary.

Features

get <id> — one preprint's full text as structured JSON or Markdown. bioRxiv/ medRxiv route Europe PMC → S3 (opt-in HTML fallback); arXiv ids route to arXiv's LaTeXML full text (native HTML → ar5iv). Latest version by default; --version selects one.
search / discover — keyword, title, abstract, or author search across Europe PMC, OpenAlex, and arXiv; topic/category/date discovery.
ingest — resumable, incremental bulk ingestion from the openRxiv S3 buckets into a chunked corpus (JSONL or Parquet) with a sidecar manifest.
MCP server — the same capabilities as tools for coding agents.
Compliance built in — an export gate degrades non-redistributable works to link-back stubs; unknown licenses are treated as non-redistributable (fail-safe).
One JATS parser shared by the Europe PMC and S3 paths; token- and section-aware chunking with deterministic, idempotent chunk ids.

Install

pip install preprint-fulltext                       # CLI + Python library + MCP server
pip install "preprint-fulltext[parquet,openalex]"   # + Parquet output, pyalex

The MCP server is built in — no extra install and no third-party MCP framework. It's a small, self-contained JSON-RPC 2.0 stdio server, so preprint-fulltext-mcp works out of the box with only the core dependencies.

Set a contact email for the Europe PMC / OpenAlex polite pools (recommended), and an OpenAlex API key if you use OpenAlex (required by OpenAlex since 2026-02-13):

export CONTACT_EMAIL="you@example.org"
export OPENALEX_API_KEY="..."            # only needed for OpenAlex discover/search

Quickstart (CLI)

# Structured full text for one preprint (Europe PMC → S3 router)
preprint-fulltext get 10.1101/2024.01.15.575000 --markdown

# Accepts a DOI, a doi.org URL, or a bioRxiv/medRxiv content URL
preprint-fulltext get https://www.biorxiv.org/content/10.64898/2026.06.13.731750v1.full --html --markdown

# Versions: the DOI resolves to the latest version by default; --version selects one
preprint-fulltext get 10.64898/2026.01.29.702557 --version 1 --source html --markdown

# arXiv: id, arxiv.org URL, or 10.48550/arXiv.* DOI — routed to arXiv LaTeXML full text
preprint-fulltext get arXiv:1706.03762 --markdown
preprint-fulltext get https://arxiv.org/abs/2401.10515 --markdown

# Search: keyword, title, or author (add --source arxiv to search arXiv)
preprint-fulltext search "cortical interneurons" -n 20
preprint-fulltext search "Fezf2" --field title
preprint-fulltext search "Min Dai" --field author
preprint-fulltext search "diffusion model" --field title --source arxiv

# Discover by topic + date window (OpenAlex)
preprint-fulltext discover --query "spatial transcriptomics" --since 2025-01 -n 100

# Bulk corpus from S3 (requester-pays; needs AWS credentials)
preprint-fulltext ingest corpus.jsonl --source s3 --server biorxiv --since 2025-06

# A free, no-AWS corpus of the open-access (CC) subset via Europe PMC
preprint-fulltext ingest corpus.jsonl --source europepmc --query "long covid"

get emits a FullText document (JSON) or Markdown (--markdown). search / discover stream one SearchHit per line (JSONL). ingest writes one Chunk per line plus a <out>_manifest.jsonl audit/resume sidecar.

Typical workflows

1. Read one paper's methods/results as text.

preprint-fulltext get 10.64898/2026.01.29.702557 --markdown > paper.md
# -> # Title / ## Abstract / ## Introduction / ## Methods / ## Results / ## Discussion

2. Build an embedding-ready corpus on a topic (free, no AWS).

# CC/open-access subset via Europe PMC — one Chunk per JSONL line
preprint-fulltext ingest cortex.jsonl --source europepmc --query "cortical interneurons" -n 500
# cortex.jsonl          -> {doi, version, chunk_id, section_kind, text, token_count, license, ...}
# cortex_manifest.jsonl -> one row per preprint (doi, version, license, n_chunks, status)

3. Build the complete corpus for a month from S3 (requester-pays).

export AWS_PROFILE=...           # needs AWS credentials; ~$0.09/GB
preprint-fulltext ingest 2025-06.jsonl --source s3 --server both --since 2025-06 --format parquet
# resumable: rerun after an interruption and it skips finished preprints (no duplicates)

4. Find papers by author or title, then fetch.

preprint-fulltext search "Min Dai" --field author -n 20 > hits.jsonl
preprint-fulltext get "$(head -1 hits.jsonl | python -c 'import sys,json;print(json.load(sys.stdin)["doi"])')" --markdown

5. Give a coding agent literature access — run preprint-fulltext-mcp and point your agent at it (see skills/preprint-fulltext/SKILL.md).

Python

from preprint_fulltext.pipeline.router import Router

result = Router().get_fulltext("10.1101/2024.01.15.575000")
if result.fulltext:
    for section in result.fulltext.sections:
        print(section.kind, section.title)

from preprint_fulltext.core.chunk import chunk_fulltext
chunks = chunk_fulltext(result.fulltext)   # embedding-ready Chunk records

MCP server

Give a coding agent live preprint access. The server exposes four tools — search_preprints, get_fulltext, get_metadata, resolve — over stdio. (Bulk ingest is intentionally not a tool: it is long-running and incurs requester-pays cost.)

mcp-name: io.github.genecell/preprint-fulltext

It's a local stdio server, so it works in Claude Code / Cursor / VS Code / Windsurf / Zed / Codex / Cline — but not the claude.ai web app (there, use the Skill instead).

Recommended: run via `uvx` (no install)

uv runs the published package on demand — nothing to pip install or keep on a PATH. Install uv once:

curl -LsSf https://astral.sh/uv/install.sh | sh    # macOS / Linux
# or:  pipx install uv  |  pip install --user uv  |  brew install uv  |  winget install astral-sh.uv

The launch command is uvx --from preprint-fulltext preprint-fulltext-mcp (the --from is needed because the run command differs from the package name). First launch downloads the package (~30 s); later launches are cached.

claude mcp add preprint-fulltext --scope user -- uvx --from preprint-fulltext preprint-fulltext-mcp
# uvx not on PATH? use its absolute path:
claude mcp add preprint-fulltext --scope user -- "$(which uvx)" --from preprint-fulltext preprint-fulltext-mcp
claude mcp get preprint-fulltext        # verify → Status: ✔ Connected

Or edit ~/.claude.json (user) / project .mcp.json:

{ "mcpServers": { "preprint-fulltext": {
  "command": "uvx",
  "args": ["--from", "preprint-fulltext", "preprint-fulltext-mcp"],
  "env": { "CONTACT_EMAIL": "you@example.org" }
} } }

Cursor: ~/.cursor/mcp.json (global) or .cursor/mcp.json (project). Windsurf: ~/.codeium/windsurf/mcp_config.json. Cline: MCP Servers → Configure. Continue: ~/.continue/config.

{ "mcpServers": { "preprint-fulltext": {
  "command": "uvx",
  "args": ["--from", "preprint-fulltext", "preprint-fulltext-mcp"],
  "env": { "CONTACT_EMAIL": "you@example.org" }
} } }

.vscode/mcp.json (workspace) or user settings.json under "mcp":

{ "servers": { "preprint-fulltext": {
  "type": "stdio",
  "command": "uvx",
  "args": ["--from", "preprint-fulltext", "preprint-fulltext-mcp"]
} } }

Or one-shot: code --add-mcp '{"name":"preprint-fulltext","command":"uvx","args":["--from","preprint-fulltext","preprint-fulltext-mcp"]}'

~/.config/zed/settings.json:

{ "context_servers": { "preprint-fulltext": {
  "source": "custom",
  "command": "uvx",
  "args": ["--from", "preprint-fulltext", "preprint-fulltext-mcp"],
  "env": {}
} } }

~/.codex/config.toml:

[mcp_servers.preprint-fulltext]
command = "uvx"
args = ["--from", "preprint-fulltext", "preprint-fulltext-mcp"]
# env = { CONTACT_EMAIL = "you@example.org" }

Or: codex mcp add preprint-fulltext -- uvx --from preprint-fulltext preprint-fulltext-mcp

Alternative: install with pip

If you already pip install preprint-fulltext, the server is on your PATH as preprint-fulltext-mcp — use "command": "preprint-fulltext-mcp" (no args) in any config above.

Env vars: set CONTACT_EMAIL (Europe PMC / OpenAlex polite pools) and OPENALEX_API_KEY (only for OpenAlex search/discover) via the config's env block, or in your shell before launching the client. See SKILL.md for the full agent-facing tool reference.

Data sources & routing

Verb	Default source	Notes
`get`	auto (Europe PMC → S3, or arXiv)	bioRxiv/medRxiv: EPMC (CC/OA subset) → S3 (complete, needs AWS creds), `--html` opt-in fallback. arXiv ids → arXiv LaTeXML full text (native HTML → ar5iv).
`search`	Europe PMC	Real relevance ranking; `--source openalex\|arxiv`.
`discover`	OpenAlex	250M+ works, OA locations, topic/date; `--source arxiv`.
`ingest`	S3 (or Europe PMC)	S3 = complete corpus; Europe PMC = free CC subset. arXiv bulk is out of scope (use arXiv's own S3 LaTeX bucket).

Configuration

Via environment variables (prefixed PREPRINT_FULLTEXT_ or the bare names below), a .env file, or a preprint-fulltext.toml:

Setting	Default	Purpose
`CONTACT_EMAIL`	–	Polite-pool identity for Europe PMC / OpenAlex
`OPENALEX_API_KEY`	–	Required by OpenAlex since 2026-02-13
`AWS_REGION`	`us-east-1`	Region for the requester-pays openRxiv buckets
`PREPRINT_FULLTEXT_CACHE_DIR`	`~/.cache/preprint-fulltext`	Content-addressed cache
`PREPRINT_FULLTEXT_CHUNK_TOKENS`	`512`	Max tokens per chunk
`PREPRINT_FULLTEXT_CHUNK_OVERLAP`	`64`	Token overlap within a section

Compliance

Corpora are for the operator's own text/data mining under the openRxiv TDM terms. preprint-fulltext does not re-host or redistribute preprint full text. Every FullText/Chunk carries its license; the export gate has two modes:

analysis (default): pass-through for your own mining.
redistribution (--redistribution): works whose license permits redistribution pass unchanged; all others are degraded to a link-back stub (metadata + URL, no body text). Unknown/ambiguous licenses are treated as non-redistributable.

Development

pip install -e ".[dev]"
pytest              # offline suite (HTTP mocked with respx, S3 with moto)
ruff check preprint_fulltext/

Live tests are opt-in (they hit the real public APIs — Europe PMC, arXiv, and the bioRxiv/medRxiv JSON API):

PREPRINT_FULLTEXT_LIVE=1 CONTACT_EMAIL=you@example.org pytest -m live   # EPMC / arXiv / medRxiv / versions
PREPRINT_FULLTEXT_LIVE_S3=1 pytest -m live_s3    # requester-pays S3 (small; needs AWS creds)

The same live smoke runs in CI on demand (Actions → live-smoke) and weekly, to catch upstream API drift; the default test workflow stays fully offline.

Agent docs (AGENTS.md, llms.txt, .cursor/rules/…, .github/copilot-instructions.md) are generated from skills/preprint-fulltext/SKILL.md:

python scripts/build_agent_docs.py

Contact

Min Dai — dai@broadinstitute.org (Gord Fishell Lab, Harvard Medical School / Broad Institute). Issues and pull requests welcome at https://github.com/genecell/preprint-fulltext.

License

BSD-3-Clause (see LICENSE). This covers the software only — retrieved preprint content remains under its author-selected license.

Available Tools

4 tools

get_fulltextC

Retrieve structured full-text sections for a preprint DOI (or URL). Resolves to the latest version by default; pass version for a specific one.

ParametersJSON Schema

Name	Required	Description	Default
`doi`	Yes
`version`	No
`as_markdown`	No

TDQS

C2.7/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description must carry the full burden. It mentions resolving to latest version by default, which is a behavioral detail, but does not disclose other traits like idempotency, authentication needs, rate limits, or error semantics. As a read-like tool, more transparency about what exactly is returned is needed.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single, concise sentence that front-loads the primary action. No unnecessary words, but lacks structured formatting (e.g., bullet points) which could improve scanability.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 3 parameters, no output schema, and no annotations, the description is too brief. It does not explain the structure of returned full-text sections, error behaviors, or boundary conditions (e.g., invalid DOI). Agents would need to infer behavior from the name and schema alone, which is insufficient.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description must explain parameters. It partially covers 'doi' and 'version' but does not mention 'as_markdown' at all. The description also says 'or URL' but the schema only requires a doi string, which could be misleading. Only 2 of 3 parameters are addressed.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool retrieves structured full-text sections for a preprint identifier (DOI or URL). It uses a specific verb and resource, distinguishing it from siblings like search_preprints (search) and get_metadata (metadata). However, it does not explicitly contrast with resolve.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus siblings (search_preprints, get_metadata, resolve). It mentions version parameter handling but lacks context about prerequisites or alternatives.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

get_metadataB

Retrieve bibliographic metadata (abstract only) for a preprint DOI.

ParametersJSON Schema

Name	Required	Description	Default
`doi`	Yes

TDQS

B3.2/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Without annotations, the description must disclose all behavioral traits. It notes 'abstract only' but omits read-only nature, error handling (e.g., invalid DOI), authentication needs, or return format.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence with no redundant words, front-loaded with verb and resource.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a simple tool with one parameter and no output schema, the description is adequate but lacks completeness: missing information on return format, error responses, or usage context.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds that 'doi' is a 'preprint DOI', but with 0% schema coverage, more detail (e.g., format, examples) is expected to compensate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description specifies a clear verb ('Retrieve') and resource ('bibliographic metadata (abstract only)') for a 'preprint DOI', distinguishing it from siblings like search_preprints (searching) and get_fulltext (full text).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool versus alternatives. Does not mention when not to use or connect to sibling tools like get_fulltext for full text.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

resolveB

Resolve between a DOI, an OpenAlex id, and a Europe PMC PPR id.

ParametersJSON Schema

Name	Required	Description	Default
`doi_or_openalex_id`	Yes

TDQS

B3.1/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries full burden. It only says 'resolve between' without explaining return values, side effects, or behavior on failure.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence, no wasted words, front-loaded with core action.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

No output schema and description does not specify return format or completeness of resolution. Incomplete for agent decision-making.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters2/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema has 0% parameter description coverage. Description adds that the parameter can be a DOI or OpenAlex id, but is ambiguous about PPR id inclusion; the parameter name contradicts the description (doesn't mention PPR).

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Description clearly states the tool resolves between three specific identifier types (DOI, OpenAlex id, Europe PMC PPR id), distinguishing it from sibling tools (search, get metadata, get fulltext).

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No explicit guidance on when to use this tool vs alternatives. It's implied for identifier conversion, but no when-not or prerequisite info.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

search_preprintsB

Search preprint full text (Europe PMC relevance or OpenAlex n-gram). field scopes to fulltext|title|abstract|author.

ParametersJSON Schema

Name	Required	Description	Default
`field`	No
`limit`	No
`query`	Yes
`source`	No

TDQS

B3.3/5.0

Behavior2/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations provided, so description must disclose behaviors. It mentions relevance/ngram sorting but fails to mention rate limits, result format, pagination, or destructive nature. 'Search' implies read-only but not explicit.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Single sentence packs purpose, sources, and field scopes without redundancy. Could be slightly clearer by splitting metadata vs. behavior, but remains efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a search tool with 4 parameters and no output schema or annotations, the description omits critical details: pagination, ordering, result structure, error handling. Incomplete for effective use.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema coverage, description adds meaning to 'field' (scopes) and 'source' (Europe PMC, OpenAlex). But 'limit' and 'query' lack explanation; query syntax, case sensitivity, or formatting not described.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it searches preprint full text, specifies two relevance methods (Europe PMC, OpenAlex n-gram), and lists field scopes. This distinguishes it from siblings like get_fulltext or get_metadata.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides context for search (preprint full text) but no explicit guidance on when to use this tool versus alternatives like get_fulltext or resolve, nor any exclusions.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.

4 tool updatesv0.1.0Jul 28, 2026
- First observedget_fulltext
- First observedget_metadata
- First observedresolve
- First observedsearch_preprints

Install Server

RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

A3.5/5.0

Disambiguation5/5

Each tool has a clearly distinct purpose: search_preprints for searching, get_fulltext for retrieving full text, get_metadata for bibliographic metadata, and resolve for ID conversion. No overlap or ambiguity.

Naming Consistency5/5

All tool names follow a consistent verb_noun pattern with snake_case (search_preprints, get_fulltext, get_metadata). 'resolve' is a single verb but fits the pattern of concise, predictable naming.

Tool Count5/5

With 4 tools, the server is well-scoped for its domain. Each tool serves a core function without being under- or over-provisioned, making it easy for agents to navigate.

Completeness5/5

The tool surface covers the essential operations for preprint fulltext retrieval: searching, full-text access, metadata retrieval, and ID resolution. There are no obvious gaps or dead ends.

Maintenance

ActivitySlowing

ResponsivenessSyncing

Resources

GitHub Repository

Need Help?

Related Servers

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Related MCP Connectors

paper-mcp B
io.github.MCPServings
Search arXiv/Semantic Scholar/OpenAlex + medical evidence (PubMed/Europe PMC) + LaTeX/PDF tools.
Research & Data Open Data
21
developer-tools-mcp-server A
com.thenextgennexus
Search GitHub, npm, PyPI, StackOverflow, ArXiv from one MCP — built for coding agents.
Developer Tools Search
72
Biorxiv B
io.github.pipeworx-io
bioRxiv + medRxiv preprint server API
Biology & Medicine Research & Data
352
morosss-sdfsdf
ai.smithery
Find academic papers across major sources like arXiv, PubMed, bioRxiv, and more. Download PDFs whe…
Research & Data Search Open Data
2

Related MCP Servers

arXiv MCP Server
Search Research & Data Documentation Access
lecigarevolant
A
license
A
quality
D
maintenance
Enables interaction with arXiv.org to search scholarly articles, retrieve metadata, download PDFs, and load article content directly into LLM context for analysis.
Updated a year ago (2025-09-27 20:02 UTC)
5
3
MIT
search-papers
Research & Data Search Documentation Access
Saidiibrahim
A
license
Not graded
quality
C
maintenance
Enables agents to search, analyze, and explore arXiv academic papers with advanced multi-field search, author lookup, category browsing, citation extraction, and bibliography export.
Updated a year ago (2025-10-01 08:32 UTC)
62
Apache 2.0
mcp-biorxiv
Biology & Medicine Research & Data
pipeworx-io
A
license
Not graded
quality
C
maintenance
Enables querying bioRxiv and medRxiv preprints, including metadata, publication status, and submission counts, through natural language or direct tool calls.
Updated 11 days ago (2026-08-26 16:43 UTC)
19
MIT
paper-search-mcp
Research & Data Search
xiaoxiaoxiaotao
F
license
A
quality
D
maintenance
Enables agents to search papers across Semantic Scholar and arXiv, read and extract text from arXiv PDFs, align records across sources, and produce structured literature-analysis digests.
Updated 5 months ago (2026-03-23 13:20 UTC)
10
1
-

Appeared in Searches

A server for finding biology preprints

Latest Blog Posts

Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)
By Om-Shree-0709 on July 25, 2026.
mcp
Agent Identity
OAuth 2.1
Your AI Chatbot Just Exposed Your CEO's Salary to an Intern
By Om-Shree-0709 on July 2, 2026.
Agent Identity
MCP Security
OAuth Delegation
Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)
By Om-Shree-0709 on June 30, 2026.
Agentic Ai
Prompt Injection
WebAssembly

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/genecell/preprint-fulltext'

If you have feedback or need assistance with the MCP directory API, please join our Discord server

preprint-fulltext

Contents

Why

Who it's for

Full text for AI-driven science

Features

Install

Quickstart (CLI)

Typical workflows

Python

MCP server

Recommended: run via uvx (no install)

Alternative: install with pip

Data sources & routing

Configuration

Compliance

Development

Contact

License

Available Tools

Tool Schema Changelog

Maintenance

Resources

Looking for Admin?

Related MCP Connectors

Related MCP Servers

Appeared in Searches

Latest Blog Posts

MCP directory API

Recommended: run via `uvx` (no install)